Explore the vast range of titles available.

The use of deep learning methods to detect plant diseases and pests based on UAV images is an important application of remote sensing technology in modern forestry. This paper uses a CenterNet-based object detection method to construct models for plant disease and pest detection. The accuracy of the models is influenced by parameter alpha, which is used to control the affine transformation in the preprocessing of CenterNet. First, different alphas are sampled for training and testing. Next, the least square method is used to fit the curve between alpha and accuracy measured by mAP (mean average precision). Finally, the equation of the curve is fitted as mAP = -0.22 * alpha2 + 0.32 * alpha + 0.42. In comparison, an automated machine learning (AutoML) method is also conducted to automatically search for the best model. The experiments are done with 5,281 images as the training dataset, 1,319 images as the verification dataset, and 3,842 images as the test dataset. The results show that the best alpha value obtained by the least square method is 0.733, and the accuracy of the corresponding model is 0.536 in mAP@[.5, .95]. In contrast, the accuracy of the AutoML method model is higher with the model accuracy of 0.545 in mAP@[.5, .95]. However, the training time and training resource consumption of the AutoML method are about 3 times that of the least square method. Therefore, in practice, a trade-off should be made according to the accuracy requirements, resource consumption, and task urgency.

【Objective】The Huai River Basin is one of China’s major rice-producing regions, where accurate and efficient estimation of paddy field evapotranspiration (ETa) is essential for sustainable agricultural water management. This study aimed to evaluate the performance of different machine learning (ML) algorithms in calculating ETa, and compare them with conventional and automated approaches.【Method】Using eddy covariance flux, microclimate, and soil observations from the Shouxian National Climate Observatory (Anhui Province, 2019), we first analyzed temporal ETa variations and their driving factors. We then estimated the ETa using three common machine learning algorithms: BP neural networks (BPNN), random forests (RF), and support vector regression (SVR). Results calculated by these methods were compared with in-situ observations. Furthermore, results calculated by the most accurate algorithm were compared with those calculated using the FAO-recommended single crop coefficient model (FAO56 PM) and the automated machine learning framework (FLAML). 【Result】As the crop grew, its ETa increased first and then decreased, with the maximum and minimum values observed in the panicle initiation-heading stage and the seedling-three leaf stage, respectively. Incoming shortwave radiation (K↓) showed the closest correlation with ETa and was the most important factor influencing ETa. Incorporating K↓ in the model could improve the accuracy of all three machine learning algorithms, with the associated R2 increasing by 51.2% and RMSE reduced by 37.7%. The RF3, which considers K↓, relative humidity (RH) and air temperature (Ta), was the optimal model for calculating ETa. Although using fewer input variables than the FAO56 PM, RF3 was more accurate in calculating ETa, increasing R2 by 6.5% in 2019 and 8.9% in 2020, while reducing RMSE by 58.2% in 2019 and 48.9% in 2020. Using the same input variables as RF3, FLAML3 worked better, increasing R2 by 1.52% and reducing RMSE by 5.6%. The improvement was more significant before the tillering stage.【Conclusion】Among all the methods we compared, FLAML3 is the most accurate and efficient for calculating ETa, due to its automated algorithm selection and hyperparameter tuning. It is robust and practical for estimating paddy field evapotranspiration in the Huai River Basin.

Investigating the phonatory processes in connected speech from high-speed videoendoscopy (HSV) demands the accurate detection of the vocal fold edges during vibration. The present paper proposes a new spatio-temporal technique to automatically segment vocal fold edges in HSV data during running speech. The HSV data were recorded from a vocally normal adult during a reading of the “Rainbow Passage.” The introduced technique was based on an unsupervised machine-learning (ML) approach combined with an active contour modeling (ACM) technique (also known as a hybrid approach). The hybrid method was implemented to capture the edges of vocal folds on different HSV kymograms, extracted at various cross-sections of vocal folds during vibration. The k-means clustering method, an ML approach, was first applied to cluster the kymograms to identify the clustered glottal area and consequently provided an initialized contour for the ACM. The ACM algorithm was then used to precisely detect the glottal edges of the vibrating vocal folds. The developed algorithm was able to accurately track the vocal fold edges across frames with low computational cost and high robustness against image noise. This algorithm offers a fully automated tool for analyzing the vibratory features of vocal folds in connected speech.

Automated machine learning (AutoML) is a young research area aiming at making high-performance machine learning techniques accessible to a broad set of users. This is achieved by identifying all design choices in creating a machine-learning model and addressing them automatically to generate performance-optimised models. In this article, we provide an extensive overview of the past and present, as well as future perspectives of AutoML. First, we introduce the concept of AutoML, formally define the problems it aims to solve and describe the three components underlying AutoML approaches: the search space, search strategy and performance evaluation. Next, we discuss hyperparameter optimisation (HPO) techniques commonly used in AutoML systems design, followed by providing an overview of the neural architecture search, a particular case of AutoML for automatically generating deep learning models. We further review and compare available AutoML systems. Finally, we provide a list of open challenges and future research directions. Overall, we offer a comprehensive overview for researchers and practitioners in the area of machine learning and provide a basis for further developments in AutoML.

Learning curves are a concept from social sciences that has been adopted in the context of machine learning to assess the performance of a learning algorithm with respect to a certain resource, e.g., the number of training examples or the number of training iterations. Learning curves have important applications in several machine learning contexts, most notably in data acquisition, early stopping of model training, and model selection. For instance, learning curves can be used to model the performance of the combination of an algorithm and its hyperparameter configuration, providing insights into their potential suitability at an early stage and often expediting the algorithm selection process. Various learning curve models have been proposed to use learning curves for decision making. Some of these models answer the binary decision question of whether a given algorithm at a certain budget will outperform a certain reference performance, whereas more complex models predict the entire learning curve of an algorithm. We contribute a framework that categorises learning curve approaches using three criteria: the decision-making situation they address, the intrinsic learning curve question they answer and the type of resources they use. We survey papers from the literature and classify them into this framework.

In recent years, deep learning (DL) has been widely studied using various methods across the globe, especially with respect to training methods and network structures, proving highly effective in a wide range of tasks and applications, including image, speech, and text recognition. One important aspect of this advancement is involved in the effort of designing and upgrading neural architectures, which has been consistently attempted thus far. However, designing such architectures requires the combined knowledge and know-how of experts from each relevant discipline and a series of trial-and-error steps. In this light, automated neural architecture search (NAS) methods are increasingly at the center of attention; this paper aimed at summarizing the basic concepts of NAS while providing an overview of recent studies on the applications of NAS. It is worth noting that most previous survey studies on NAS have been focused on perspectives of hardware or search strategies. To the best knowledge of the present authors, this study is the first to look at NAS from a computer vision perspective. In the present study, computer vision areas were categorized by task, and recent trends found in each study on NAS were analyzed in detail.

Automated machine learning (AutoML) seeks to automatically select, compose, and parametrize machine learning algorithms, so as to achieve optimal performance on a given task (dataset). Although current approaches to AutoML have already produced impressive results, the field is still far from mature, and new techniques are still being developed. In this paper, we present ML-Plan, a new approach to AutoML based on hierarchical planning. To highlight the potential of this approach, we compare ML-Plan to the state-of-the-art frameworks Auto-WEKA, auto-sklearn, and TPOT. In an extensive series of experiments, we show that ML-Plan is highly competitive and often outperforms existing approaches.

Evaluation of slope failures, which cause significant loss of life and property comparable to natural disasters such as earthquakes, floods and hurricanes, is one of the main areas of interest in geotechnical engineering. Although traditional and modern methods have been developed for slope stability analysis, the importance given to computer-based approaches has increased in recent years. In this study, we investigated the effectiveness of advanced machine learning (ML) algorithms in classification-based slope stability assessment. In this context, examining the impact of input parameters, such as slope height, slope angle, unit volume weight, internal friction angle of the soil, cohesion of the slope material, and water pressure ratio on the slope stability potential and a comparative analysis was performed on the ML algorithms. On the other hand, automated machine learning (AutoML) approaches were used to make rapid and comprehensive comparisons of ensemble, boosting, bagging and traditional ML algorithms to simplifying application development. The weighted ensemble learning algorithm provided by the AutoGluon package outperformed other algorithms in both testing and training accuracy, achieving an impressive rate of 97.5%, according to the obtained results. All algorithms included in the study performed well, with NeuralNetTorch and CatBoost securing the second position with an accuracy rate of 95%. Furthermore, when evaluating the importance of features using the best algorithm, it can be seen that unit volume weight and internal friction angle of soil had the highest weights, 0.225 and 0.200, respectively, indicating their importance in classifying slope stability. In conclusion, our research significantly advanced slope stability assessment, achieving one of the highest accuracy of 0.975 among various classification-based studies.

Slope failures lead to large casualties and catastrophic societal and economic consequences, thus potentially threatening access to sustainable development. Slope stability assessment, offering potential long-term benefits for sustainable development, remains a challenge for the practitioner and researcher. In this study, for the first time, an automated machine learning (AutoML) approach was proposed for model development and slope stability assessments of circular mode failure. An updated database with 627 cases consisting of the unit weight, cohesion, and friction angle of the slope materials; slope angle and height; pore pressure ratio; and corresponding stability status has been established. The stacked ensemble of the best 1000 models was automatically selected as the top model from 8208 trained models using the H2O-AutoML platform, which requires little expert knowledge or manual tuning. The top-performing model outperformed the traditional manually tuned and metaheuristic-optimized models, with an area under the receiver operating characteristic curve (AUC) of 0.970 and accuracy (ACC) of 0.904 based on the testing dataset and achieving a maximum lift of 2.1. The results clearly indicate that AutoML can provide an effective automated solution for machine learning (ML) model development and slope stability classification of circular mode failure based on extensive combinations of algorithm selection and hyperparameter tuning (CASHs), thereby reducing human efforts in model development. The proposed AutoML approach has the potential for short-term severity mitigation of geohazard and achieving long-term sustainable development goals.